Research Engineer / Scientist, Reinforcement Learn
Responsibilities
- Own and pursue research to improve model capability on long-horizon legal reasoning and agentic workflows.
- Design and run post-training experiments using supervised fine-tuning and reinforcement learning on leading open-weight models.
- Develop reward functions and verifiers for semi-verifiable tasks, including rubrics, learned preference models, and expert preference data.
- Run and debug large-scale training while addressing divergence, reward hacking, and instability.
- Build and use rigorous evaluations to track improvements and determine what ships.
- Design, implement, test, and debug code across the research stack.
Requirements
- Hands-on experience post-training large language models with supervised fine-tuning, reinforcement learning, and preference optimization.
- Direct ownership of training runs and results.
- Deep machine learning fundamentals and experience getting distributed training runs working reliably.
- Strong Python engineering skills, including production-quality code and end-to-end system ownership.
- Research experience in reinforcement learning for language models or reward modeling.
- Ability to move quickly from experiments to shipped improvements.
- Publications are welcome but not required.
Recommended Jobs
International Tax Senior Manager - Real Estate
Take your tax career global with our market-leading International Tax team. We are looking for an Senior Manager with a background in International tax to join a market-leading team specialising i…
Lead Counsel, Commercial and Marketing, EMEA (Hiring Immediately)
Our mission at ŌURA is to empower every person to own their inner potential. Our award-winning products help our global community gain a deeper knowledge of their readiness, activity, and sleep quali…
Field Service Engineer
Field Service Engineer – Diesel Power Generation Location: London (Regional Patch) Salary: Up to £40,000 (DOE) + Door to door paid travel + Full Industry-Leading Training Are you an e…
.NET Developer
.NET Developer, .NET 10.0, C# 14, Agile - London (Tech stack: .NET Developer, .NET 10.0, ASP.NET Core, C# 14, Azure, Angular 21, Vue.js, TypeScript, Multithreading, RESTful, ASP.NET Core Web API, EF …
Sales Support Executive
Are you ready to take your administrative skills to the next level? We’re seeking a proactive and detail-oriented individual to join our client’s dynamic vendor sales team. As a Sales Support Ex…
Assistant Manger
ABOUT GREYSTAR Greystar is a leading, fully integrated global real estate platform offering expertise in property management, investment management, development, and construction services in insti…
Software Developer - High Performance Trading Systems
Software Developer – High Performance Trading Systems Location: London (On-site) £400k+ total comp We are looking for a talented software engineer to join a high-performing team responsib…
Employment Law Solicitor
Top Legal 500 located in the heart of the City are currently seeking an Employment Law Solicitor of 2-5 years PQE. This is your chance to work in an environment that values innovation, collaboration,…
Client Manager (London)
Forvis Mazars is a leading global professional services network providing audit & assurance, tax, and advisory services. Forvis Mazars in the UK spans 14 offices across the nation and has over 3,400 …